Spatio-Temporal Knowledge Transfer for Urban Crowd Flow Prediction via Deep Attentive Adaptation Networks

Accurately predicting the urban spatio-temporal data is critically important to various urban computing tasks for smart city related applications such as crowd flow prediction and traffic congestion prediction. Existing models especially deep learning based approaches require a large volume of training data, whose performance may degrade remarkably when the data is scarce. Recent works try to transfer knowledge from the intra-city or cross-city multi-modal spatio-temporal data. However, the careful design of what to transfer and how between the multi-modal spatio-temporal data needs to be determined in advance. There still lacks an end-to-end solution that can automatically capture the common cross-domain knowledge. In this paper, we propose a Deep Attentive Adaptation Network model named ST-DAAN to transfer cross-domain Spatio-Temporal knowledge for urban crowd flow prediction. ST-DAAN first maps the raw spatio-temporal data of source domain and target domain to a common embedding space. Then domain adaptation is adopted on several domain-specific layers through adding a domain discrepancy penalty to explicitly match the mean embeddings of the two domain distributions. Considering the complex spatial correlation in many urban spatio-temporal data, a global attention mechanism is also designed to enable the model to capture broader spatial dependencies. Using urban crowd flow prediction as a demonstration, we conduct experiments on five real-world large datasets over both intra- and cross-city transfer learning. The results demonstrate that ST-DAAN outperforms state-of-the-art methods by a large margin.

Automated summary

This paper proposes a Deep Attentive Adaptation Network model named ST-DAAN for transferring cross-domain Spatio-Temporal knowledge for urban crowd flow prediction. The model maps raw spatio-temporal data to a common embedding space, adopts domain adaptation, and incorporates a global attention mechanism to capture spatial dependencies. Experimental results demonstrate that ST-DAAN outperforms state-of-the-art methods significantly.